
Use **Filter Widget** when the dashboard should let users change what they are looking at without editing each widget separately.

## Add the widget

1. Open a dashboard.
2. Click **Dashboard options** next to the time range.
3. Click **Add widget**.
4. Choose **Filter Widget**.

## Configure the filter widget

When the setup screen opens:

1. Enter the widget name.
2. Add an optional description.
3. Choose which widgets it should affect, or leave it broad if the flow allows it.
4. Decide how filters should be displayed.
5. Build the filter list.

The widget supports different display styles such as:

- toggles
- radio buttons
- dropdowns

## Build the filter list

For each filter item:

1. enter a filter name
2. define the filter conditions
3. decide whether it should start active
4. duplicate or reorder items if needed

## When to use Filter Widget

Use **Filter Widget** when:

- the same filter should drive several widgets
- users need quick dashboard-level switching between common states
- the dashboard would be too noisy if each widget had separate controls

## Tips

- keep the filter names simple
- avoid creating too many overlapping filter options
- use this widget near the top of large dashboards



Use the Filter Widget to create a shared filtering control that drives one widget, several widgets, or the whole dashboard.

Filter Widget


Use **Streaming** when the dashboard should include live visual context from an **AI Vision Device**.

This widget is useful when people need to watch the live situation while also reviewing charts, KPIs, or routing information on the same page.

## Navigation

Open a dashboard, enter edit mode if needed, then choose **Add widget**.

Use **Streaming** when the dashboard should include a live video area.

## When to use it

The Streaming widget appears directly on the dashboard as a live video tile.

It works best when it has enough space to stay readable.

## Add the widget

1. Open a dashboard.
2. Click **Add widget**.
3. Choose **Streaming**.

## Configure the stream

When the widget opens:

1. Enter the widget name.
2. Select the **AI Vision Device**.
3. Choose the video rotation if needed.
4. Turn on the snapshot file name if you want it, and choose where it sits on the video.
5. Review the preview.
6. Save the widget.

## Show the snapshot file name

While the stream runs, the device saves an image for each frame it inspects and reports the file
name it used. The widget can show that name on top of the video.

This is **off unless you turn it on**, because the label covers a small part of the image. Switch
on **Show snapshot file name** when editing the widget.

This helps when someone needs to:

- match what they are watching to the stored image
- quote an exact file name when reporting a problem
- confirm the device is still saving images

The coloured dot beside the name shows whether the image has finished uploading:

- **green** — the image is saved and can be opened
- **amber** — the device has captured it but the upload is still in progress

Use **File Name Position** to move the label to any corner of the video. **Bottom left** is the
default, so the label stays clear of the player controls.

The device reports its most recent images, newest first. Click the arrow on the label to see the
others, and hover any of them for the full file name and the time it was captured.

Notes:

- The label only appears while live view is running, and clears when the stream stops.
- If the device is not reporting file names, no label appears.

## When to use Streaming

Use **Streaming** when:

- users need a live video view on the dashboard
- a visual check should sit beside charts, KPIs, or routing information
- the dashboard is used for active monitoring instead of historical review only

## Tips

- Use this widget only when the related AI Vision Device is available.
- Keep the widget large enough to remain useful.
- Place it near the widgets that describe the same device or process.



Use the Streaming widget to show live video from an AI Vision Device inside a dashboard.

Streaming


![Image annotation page](/docs/data-sources/image-annotation-01.png)

Open a dataset, then click an image to open this page.

This page is where you review one image, work on labels, and move between images without going back.

## Auto annotation

Use the button at the top when you want the system to help with labels.

- **Generic Model** runs the general auto annotation option
- **Custom Model** runs the custom auto annotation option
- **Batch Custom Model** runs the custom option on more images
- **Pallet Geometry & Nails** helps with pallet structure and nail labels

The main button uses the option that is currently selected.

## Auto detection options

Open **Annotation** on the left when you want to change how auto annotation works.

![Generic model settings](/docs/data-sources/image-annotation-02.png)

### Generic model

Use **Generic model** when you want the system to find common objects from your label list.

- choose the detection model
- choose which labels to include
- add simple label descriptions if needed
- adjust how strict the results should be

This is usually the easiest place to start.

![Custom model settings](/docs/data-sources/image-annotation-03.png)

### Custom model

Use **Custom model** when you already trained a model for this data source.

- pick the trained model
- adjust confidence
- adjust overlap filter
- set how many boxes can be added for each label

This is usually better when the generic option is not accurate enough.

![Click To Annotate settings](/docs/data-sources/image-annotation-04.png)

### Click To Annotate

Use **Click To Annotate** when you want help on one object at a time.

- choose the label on the left
- hold **Option**
- click the object in the image

If **Classify clicked objects** is on, the system tries to decide the label for you. If it is off, it uses the label you selected on the left.

### Included labels

Use **Included labels** to choose which labels the system should work with.

If you do not need every label, keep only the ones you want. This usually gives cleaner results.

### Label descriptions

You can add short words or phrases for each label.

This helps the system understand what each label means.

### Results

You can make the result more loose or more strict.

- **Confidence**: lower finds more objects, higher keeps only stronger matches
- **Overlap filter**: removes duplicate boxes
- **Max boxes per label**: limits how many boxes are added

### Request mode

You can choose how the result is returned.

- **Sync** shows the result here right away
- **Async** finishes in the background and saves when ready

## View

Use the **View** section on the left to change how you look at the image.

- **Turn selection off/on** changes whether you are selecting labels
- **Show active only** shows only the label you are working on

## Actions

Use the **Actions** section on the left for common image work.

- **Include zone** adds an area to include
- **Exclude zone** adds an area to ignore
- **Annotation** opens annotation options
- **Shortcuts** shows keyboard shortcuts
- **Copy labels** copies labels to other images
- **Bulk edit labels** updates labels in bulk
- **Delete image** removes the image

## Labels

Use the **Labels** section on the left to work with your label list.

- click a label to make it active
- the number next to each label shows how many of that label are in the image
- **Configure labels** opens the dataset label list

## Image list

The images on the right help you move through the dataset.

- click another image to open it
- the highlighted image is the one you are working on now
- the count at the top shows how many images are in the list

## Read next

- [Dataset Page](/docs/ai-vision/dataset-page)
- [Datasets](/docs/ai-vision/datasets)


Browse Guides

Filter Widget

Add the widget

Configure the filter widget

Build the filter list

When to use Filter Widget

Tips